© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4456
    Prev
    Next
    INDEX
    Explanations

    introduces discussions or debates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apadam
    2.03
     esenciales
    1.96
    apatos
    1.87
     divino
    1.86
     saisir
    1.86
     finisher
    1.84
    urable
    1.84
    }\|^
    1.83
    alone
    1.82
    utom
    1.82
    POSITIVE LOGITS
     discussions
    1.69
     discussion
    1.68
     criticisms
    1.53
     criticism
    1.50
     controversy
    1.47
     rumors
    1.44
     scrutiny
    1.42
     discuss
    1.42
     debate
    1.40
     debates
    1.40
    Activations Density 0.214%

    No Known Activations